The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016

K. A. Lee, V. Hautamäki, T. Kinnunen, A. Larcher, C. Zhang, A. Nautsch, T. Stafylakis, M. Rouvier, W. Rao, F. Alegre, J. Ma, M. W. Mak, A. K. Sarkar, H. Delgado, R. Saeidi, H. Aronowitz, A. Sizov, H. Sun, T. H. Nguyen, G. WangB. Ma, V. Vestman, M. Sahidullah, M. Halonen, A. Kanervisto, G. Le Lan, F. Bahmaninezhad, S. Isadskiy, C. Rathgeb, C. Busch, G. Tzimiropoulos, Q. Qian, Z. Wang, Q. Zhao, Tianzhou Wang, H. Li, J. Xue, S. Zhu, R. Jin, T. Zhao, P. M. Bousquet, M. Ajili, W. B. Kheder, D. Matrouf, Z. H. Lim, C. Xu, H. Xu, X. Xiao, E. S. Chng, B. Fauve, K. Sriskandaraja, V. Sethu, D. A.L. Thomsen, Z. H. Tan, M. Todisco, N. Evans, Haizhou Li, J. H.L. Hansen, J. F. Bonastre, E. Ambikairajah, Gang Liu, Weiwei Lin

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    13 Citations (Scopus)
    135 Downloads (Pure)


    The 2016 speaker recognition evaluation (SRE'16) is the latest edition in the series of benchmarking events conducted by the National Institute of Standards and Technology (NIST). I4U is a joint entry to SRE'16 as the result from the collaboration and active exchange of information among researchers from sixteen Institutes and Universities across 4 continents. The joint submission and several of its 32 sub-systems were among top-performing systems. A lot of efforts have been devoted to two major challenges, namely, unlabeled training data and dataset shift from Switchboard-Mixer to the new Call My Net dataset. This paper summarizes the lessons learned, presents our shared view from the sixteen research groups on recent advances, major paradigm shift, and common tool chain used in speaker recognition as we have witnessed in SRE'16. More importantly, we look into the intriguing question of fusing a large ensemble of sub-systems and the potential benefit of large-scale collaboration.

    Original languageEnglish
    Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    PublisherInternational Speech Communication Association (ISCA)
    Number of pages5
    ISBN (Print)978-1-5108-4876-4
    Publication statusPublished - 2017
    MoE publication typeA4 Conference publication
    EventInterspeech - Stockholm, Sweden
    Duration: 20 Aug 201724 Aug 2017
    Conference number: 18

    Publication series

    NameInterspeech: Annual Conference of the International Speech Communication Association
    ISSN (Electronic)2958-1796


    Internet address


    • Benchmark
    • Call My Net
    • Fusion
    • Speaker recognition evaluation


    Dive into the research topics of 'The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016'. Together they form a unique fingerprint.

    Cite this